Alternatives and similar repositories for emergent-misalignment:

Users that are interested in emergent-misalignment are comparing it to the libraries listed below

• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆85Updated this week
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆198Updated 5 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆170Updated 4 months ago
• METR / task-standard
  METR Task Standard
  ☆146Updated last month
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆165Updated last week
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆192Updated 3 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆192Updated 6 months ago
• OSU-NLP-Group / GrokkedTransformer
  Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'
  ☆186Updated 3 months ago
• google-deepmind / mishax
  ☆124Updated last week
• METR / public-tasks
  ☆87Updated 2 weeks ago
• ConsequentAI / fneval
  Functional Benchmarks and the Reasoning Gap
  ☆84Updated 5 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆91Updated last month
• jerber / lang-jepa
  ☆106Updated 3 months ago
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆98Updated last year
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆101Updated this week
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆168Updated 2 months ago
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆497Updated this week
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆237Updated last year
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆235Updated 3 months ago
• jacobdunefsky / transcoder_circuits
  ☆66Updated 4 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆73Updated 4 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆91Updated last year
• LeonGuertler / TextArena
  A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
  ☆101Updated this week
• UKGovernmentBEIS / control-arena
  ControlArena is a suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alp…
  ☆41Updated this week
• callummcdougall / sae_visualizer
  ☆26Updated 11 months ago
• ScalingIntelligence / Archon
  Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.
  ☆166Updated 3 weeks ago
• aypan17 / machiavelli
  ☆130Updated 4 months ago
• google-deepmind / dangerous-capability-evaluations
  ☆53Updated 6 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆214Updated 5 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆117Updated 2 years ago